research
∙
02/10/2023
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
"Forward-only" algorithms, which train neural networks while avoiding a ...
share
research
∙
11/21/2022
Neural networks trained with SGD learn distributions of increasing complexity
The ability of deep neural networks to generalise well even when they in...
research
∙
02/09/2022
Optimal learning rate schedules in high-dimensional non-convex optimization problems
Learning rate schedules are ubiquitously used to speed up and improve op...
research
∙
01/31/2022
Fluctuations, Bias, Variance Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
From the sampling of data to the initialisation of parameters, randomnes...
research
∙
01/06/2022
The dynamics of representation learning in shallow, non-linear autoencoders
Autoencoders are the simplest neural network for unsupervised learning, ...
research
∙
02/23/2021
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
A recent series of theoretical works showed that the dynamics of neural ...
research
∙
11/24/2020
The dynamics of learning with feedback alignment
Direct Feedback Alignment (DFA) is emerging as an efficient and biologic...
research
∙
09/20/2020
Epidemic mitigation by statistical inference from contact tracing data
Contact-tracing is an essential tool in order to mitigate the impact of ...
research
∙
03/02/2020